© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15233
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and their associated verbs, particularly in reference to groups of people

    oai_token-act-pair · gemini-2.0-flash

    Opinions and Arguments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     étions
    -0.50
     שוליים
    -0.48
     nationaux
    -0.48
     alimentaires
    -0.46
     récomp
    -0.46
    jep
    -0.46
    ræ
    -0.45
     Fokus
    -0.43
     doulou
    -0.43
     relatifs
    -0.43
    POSITIVE LOGITS
    참고
    0.73
    出版年
    0.71
    MessageTagHelper
    0.68
    ècie
    0.65
    PreferredItem
    0.62
     ویکی‌پدی
    0.61
     SafeMath
    0.57
    XmlEnum
    0.57
     think
    0.57
    IndentedString
    0.56
    Activations Density 1.703%

    No Known Activations